EP0522591A2 - Datenbankauffindungssystem zur Beantwortung natursprachlicher Fragen mit dazugehörigen Tabellen - Google Patents

Datenbankauffindungssystem zur Beantwortung natursprachlicher Fragen mit dazugehörigen Tabellen Download PDF

Info

Publication number
EP0522591A2
EP0522591A2 EP92111820A EP92111820A EP0522591A2 EP 0522591 A2 EP0522591 A2 EP 0522591A2 EP 92111820 A EP92111820 A EP 92111820A EP 92111820 A EP92111820 A EP 92111820A EP 0522591 A2 EP0522591 A2 EP 0522591A2
Authority
EP
European Patent Office
Prior art keywords
database
retrieval
natural language
phrases
formula
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
EP92111820A
Other languages
English (en)
French (fr)
Other versions
EP0522591B1 (de
EP0522591A3 (en
Inventor
Ikuko c/o Mitsubishi Denki Takanashi
Shozo c/o Mitsubishi Denki Kondo
Katsushi c/o Mitsubishi Denki Suzuki
Kazutomo c/o Mitsubishi Denki Naganuma
Yoshiko c/o Mitsubishi Denki Itabashi
Chikako c/o Mitsubishi Denki Kimura
Naohito c/o Mitsubishi Denki Inaba
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mitsubishi Electric Corp
Original Assignee
Mitsubishi Electric Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from JP3171217A external-priority patent/JP2596260B2/ja
Application filed by Mitsubishi Electric Corp filed Critical Mitsubishi Electric Corp
Publication of EP0522591A2 publication Critical patent/EP0522591A2/de
Publication of EP0522591A3 publication Critical patent/EP0522591A3/en
Application granted granted Critical
Publication of EP0522591B1 publication Critical patent/EP0522591B1/de
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2452—Query translation
    • G06F16/24522—Translation of natural language queries to structured queries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2452—Query translation
    • G06F16/24526—Internal representations for queries
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10—TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10S—TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00—Data processing: database and file management or data structures
    • Y10S707/99931—Database or file accessing

Definitions

  • This invention relates generally to database retrieval systems for retrieving information stored in a database, and, more particularly, to database retrieval systems for retrieving information stored in a database using natural language expressions.
  • Fig. 1 is a diagram illustrating a conventional database retrieval system for retrieving data from a table formatted database in response to a natural language query.
  • a natural language query is a request for data that is set forth in a natural language, such as English, Japanese, French, etc.
  • the illustrated database retrieval system is described in more detail in "Kinukawa, A Natural Language Interface Processor Based on the Hierarchical-Tree Structure Model of Relation Table. Journal of Information Processing Society of Japan , Vol.27, No.5 (1986), pp.499-509." This system is designed to process queries in Japanese. For the examples described below, the English translations of Japanese words and phrases are provided in parenthesis.
  • the database retrieval system shown in Fig. 1 includes an input unit 2, such as a keyboard, for entering a natural language query 1.
  • the system also includes a communications controller 3 for forwarding the natural language query 1 to a retrieval sentence analysis unit 5.
  • the retrieval sentence analysis unit 5 processes the input query 1 to produce a hierarchical model of the query.
  • the system additionally includes a word dictionary 4, that is constructed on the basis of the content of a database 9, and a hierarchical table model 6 for hierarchically expressing the content of the database.
  • the dictionary 4 and hierarchical table model 6 are used by the retrieval sentence analysis unit 5 in analyzing the natural language query 1.
  • the retrieval sentence analysis unit 5 performs both vocabulary analysis and syntactic/semantic analysis on the natural language query 1.
  • the retrieval sentence analysis unit 5 produces a retrieval sentence analysis result 7 as output that is forwarded to a retrieval processing unit 8.
  • the retrieval processing unit 8 uses the retrieval sentence analysis result 7 to retrieve data from the database 9.
  • the depiction of the conventional database retrieval system shown in Fig. 1 is a functional description intended to show the interaction between the respective components of the system.
  • the components shown in Fig. 1 are, in fact, implemented in a data processing system 10, such as that shown in Fig. 2.
  • the data processing system 10 includes a central processing unit (CPU) 11, a memory 12, the communications controller 3, an output device 17 and the input unit 2. Each of these components is coupled to a bus 13.
  • the retrieval sentence analysis unit 5 and the retrieval processing unit 8 are implemented in software that is executed by the CPU 11 (Fig. 2).
  • the software is stored in the memory 12.
  • the word dictionary 4 (Fig. 1), the hierarchical model table 6 and the database 9 are stored within the memory 12 (Fig. 2).
  • Fig. 3a provides a more detailed depiction of an example of the word dictionary 4.
  • the dictionary includes a plurality of entries, and each entry includes three fields.
  • the header field identifies the term or phrase associated with the entry, whereas the part of speech field identifies the part of speech of the term or phrase.
  • the type field identifies the type of term or phrase that is used. In the example shown in Fig. 3a, the types are "item name" and "data expression word”.
  • Fig. 3b provides a more detailed depiction of the hierarchical table model 6.
  • This model 6 sets forth the hierarchical relationship between the respective tables.
  • Each table specifies a number of attributes.
  • table 14 includes the attributes of "date”, “commodity code”, “commodity group code”, and "sales".
  • the "commodity code” attribute is also an attribute in table 16, which is hierarchically related with table 14.
  • the attribute of "commodity group code” is an attribute of both table 16 and table 18.
  • the table 14 is a higher order table than tables 16 and 18.
  • table 16 is a higher order than table 18.
  • This hierarchical table model is consistent with the relational model for data proposed by E. F. Todd in "A Relational Model of Data for Large Shared Data Banks," Communications of the ACM , June 1970, pp. 377-387.
  • Table 3c provides illustration of the database 9.
  • the database 9 includes table A, table B and table C.
  • Each of the tables A, B, C includes different types of information.
  • table A contains sales information
  • table B includes commodity information
  • table C includes commodity group information.
  • a natural language query 1 is entered using the input unit 2.
  • the query is entered simply by typing the query.
  • the query 1 is then passed to the conversation control unit 3, which forwards the query to the retrieval sentence analysis unit 5.
  • the retrieval sentence analysis unit 5 parses the query into a hierarchical structure of words or phrases that is output as the retrieval sentence analysis result 7.
  • the retrieval sentence analysis unit 5 first chops the query into words or phrases.
  • the query is chopped into the phrases "chokoreeto rui" and "uriage”.
  • the terms "no" and “ha” are zyoshi, whose significance will be described in more detail below.
  • the retrieval sentenced analysis unit 5 references the word dictionary 4 to determine that "chokoreeto rui" (chocolates and the like) is a data expression word (see Fig. 3a).
  • the retrieval sentence analysis unit 5 also determines that "uriage” (sales) is an attribute item name, respectively.
  • the word dictionary 4 indicates that both of these phrases are nouns.
  • the dictionary 2 is not referenced for the zyoshi "ha” and "no".
  • Syntax and semantic analysis is then performed on the query.
  • syntactic analysis is performed to process the syntax or the query in order to understand the role each phrase serves in the query.
  • Semantic analysis is performed to understand what is being requested by the query.
  • semantic analysis is performed to relate the meaning of the query to the database entries.
  • the semantic analysis relies on the hierarchical table model 6 (see Fig. 3b) to ascertain that "chokoreeto rui” (chocolates and the like) is an attribute data expression word of a commodity group in table 18 (i.e., table C in Fig. 3c) and "uriage" (sales) is an item name in the table 14 (i.e. table A in Fig. 13c).
  • the hierarchical table model 6 indicates that table 14 is a higher order table than table 18.
  • Figs. 4a, 4b and 4c show dictionaries used in a second conventional database retrieval system, as disclosed in Japanese Patent Laid-Open Publication No. 59-99539.
  • information on column name in a file, information on data item name, and information on a file name that possesses a common column name or data name are stored according to file names of a data file that is contained in a database.
  • Fig. 4a represents a dictionary in which one of the database files contains the column name of a file. The dictionary also holds information regarding the order in which the column is contained in the file and additionally holds information regarding synonyms of the column name (i.e., file numbers and column attribute numbers of columns that are synonymous with the named column).
  • Fig. 4a represents a dictionary in which one of the database files contains the column name of a file.
  • the dictionary also holds information regarding the order in which the column is contained in the file and additionally holds information regarding synonyms of the column name (i.e., file numbers and column attribute numbers of columns that are synonymous with the
  • FIG. 4b shows an analogous dictionary in which one of the files contains a data column name, and the dictionary stores a position at which the named column is contained in the file. Lastly, the dictionary stores information regarding synonyms of the data column name.
  • Fig. 4c shows a dictionary holding information as to semantically identical data columns that are connected as synonyms.
  • Fig. 5 is the designated format for input queries for the second conventional system. This format requires that queries be entered as a number of entries, wherein each entry includes two fields; a noun filed and a particle or auxiliary field.
  • queries be entered as a number of entries, wherein each entry includes two fields; a noun filed and a particle or auxiliary field.
  • the input query for the second conventional system would be as follows. The first noun field would be entered as "chokoreeto rui" and the corresponding particle field would be entered as "no”. Further, the second noun field would be entered as "uriage” and the particle field would be entered as "ha”.
  • the information retrieval system of the present invention is used for retrieving information from a database.
  • the information retrieval system includes a parser for parsing a natural language input query into constituent phrases.
  • the parser outputs a syntax analysis result.
  • the system also includes a virtual table for converting phrases of the natural language query to retrieval keys that are possessed by the database.
  • the virtual table accounts for particles that modify the phrases in the input query.
  • a collating unit is provided in the system for preparing a database retrieval formula from the syntax analysis result by selecting a virtual table that it is used to convert the phrases to the keys possessed by the database.
  • the system includes a retrieval execution unit for retrieving data from the database on the basis of the database retrieval formula.
  • the information retrieval system may also include an additional table for converting an undetermined value phrase in the natural language query into a determined value phrase in the database based on the syntax analysis result. Still further, the information retrieval system may include a terminology dictionary for identifying entries in the virtual table that are to be used in converting phrases of the natural language query. The dictionary includes words representing times and the dictionary is used by the parser in obtaining the syntax analysis result. When the terminology dictionary is used, the system may also include a time interval definition table in the virtual table for defining dates corresponding to words representing time. Lastly, the system may include a database retrieval formula conversion unit for generating a formula in a database retrieval language from the database retrieval formula.
  • Fig. 6 shows the construction and flow of processing of a first preferred embodiment of the present invention which provides a database retrieval system that responds to a natural language query 1.
  • the system may be implemented on a data processing system as shown in Fig. 2.
  • This first preferred embodiment includes an input unit 2, a conversation control unit 3 and a database 9 like that employed in the conventional system of Fig. 1.
  • These components are implemented in the data processing system 2 as discussed for the first conventional system.
  • the preferred embodiment differs from the conventional system in several respects. These distinctions are highlighted below.
  • the first preferred embodiment also includes a parser 22 for parsing an input natural language query into its constituent parts.
  • the parser 22 uses a grammar table 24 and a terminology dictionary 26.
  • the grammar table 24 holds information for regulating the relation in a Japanese sentence
  • the terminology dictionary 26 defines the part of speech and meaning of each word in the query 22.
  • the terminology dictionary 26 is similar to the conventional word dictionary 4 shown in Fig. 1, the terminology dictionary of Fig. 6 differs in that is includes a column for a semantic marker (see Fig. 7). The role of the semantic marker is described in more detail below.
  • a column for a semantic ID (see Fig. 7) and a column for a correspondence item are also provided.
  • the parser analyzes the input query 22 to determine the subject, predicates and other parts of speech in the input natural language query 22.
  • the system of Fig. 6 differs substantially from the conventional system of Fig. 1 in that the system of Fig. 6 includes a virtual table 28.
  • the virtual table is a natural language conversion virtual table held in memory 12 (Fig. 2), for designating which table in the database 9 is to be searched to find the data requested in the query 22.
  • variable data which continuously changes in accordance with "event”.
  • Variable data is also referred to as a cumulative file.
  • Fixed data having the same characteristics are grouped to form a virtual table. Further, a virtual table is formed by adding variable data to those fixed data items which are strongly related thereto.
  • the virtual table 28 is composed of a number of tables (i.e. tables 1 - 8) as shown in Figs. 8a - 8c. Each one of the entries in these tables includes a field for a "surface restriction” (see Figs. 8a - 8c) and a field for a "correspondence attribute" is included for each entry.
  • the surface restriction field is filled with data only for variable data.
  • the surface restriction field is used to store particles which modify each header word of the input natural language and which determine the value of the "correspondence attribute" in combination with the header word. That is, the surface restriction is an item that is provided for performing a further selection when a plurality of corresponding attributes are possible for a header word.
  • the correspondence attribute may designate another virtual table, a database entity table, or an operation entity table. Designation of another virtual table indicates that detailed data are stored in the other table. Further, the storage in this fashion is used in an algorithm for selecting a virtual table. Specifically, if a virtual table is designated in a correspondence attribute field, the designated virtual table is selected with priority.
  • the system of Fig. 6 also includes a collating unit for retrieving data from the database 9 by referencing the virtual table 28 using the analysis result that is output from the parser 5.
  • the collating unit may be implemented in software that is executed by the CPU 11 (Fig. 2) and stored in memory 12.
  • the system further includes a database formula generation unit 32 for converting an entity table logic formula from the collating unit into a database retrieval formula.
  • the database retrieval formula is used by a retrieval unit that retrieves data from the database 9.
  • zyoshi modifies the phrase “Chokoreeto rui” (chocolates and the like) to indicate that "Chokoreeto rui” is the object of a prepositional phrase.
  • the zyoshi “no” follows the word “sengetsu” to indicate that "sengetsu” is the object of a prepositional phrase.
  • zyoshi modifies the term “uriage” (sales) to indicate that "uriage” is the subject of the query.
  • the zyoshi help to construct the hierarchical model shown in Fig. 9 that is output from the parser 22.
  • the natural language input query 20 (Fig. 6) is input by the input unit 2 and received by the communications controller 3.
  • the communication controller directs the input query to the parser 22.
  • the grammar table 24 is used by the parser 22 to examine grammatical rules that help to parse the table into an appropriate syntax tree like that shown in Fig. 9.
  • the parser 22 also uses the terminology dictionary 26 to determine which of the tables in the virtual table 28 should be examined. Specifically, the "item" column of the terminology dictionary, as shown in Fig. 7, is examined.
  • the collating unit 30 determines which of the tables in the virtual table 28 will be utilized. For the example of natural language query 20, table 1 (see Fig. 8a) is examined. The entries for the corresponding terms are examined in the table. The correspondence attribute field of the entries specify the table in the database 9 (Fig. 6) and entry where information regarding the term of interest may be found, another correspondence table or an indication that the desired data is calculated as a mathematical function.
  • the information retrieved by the collating unit 30 i.e., the entity table logical formula
  • the database retrieval formula is passed from the database formula generation unit 32 to the retrieval unit 34, which retrieves the appropriate data from the database 9.
  • the retrieved data is then output to the output device 17 (Fig. 2).
  • a natural language query 1 "Chokoreeto rui no sengetsu no uriage ha?” (Sales of chocolates and the like in the last month?) is entered using the input unit 2.
  • the communications controller 3 passes this query to the parser 22.
  • Retrieval order and operation order of the retrieval language are defined at the communications controller 3.
  • the parser 22 parses the query according to known strategies for parsing Japanese queries to produce a syntax analysis result (like syntax tree shown in Fig. 9).
  • the parser 5 uses the grammar table 34 and the terminology dictionary 26 in performing its parsing.
  • the grammar table 24 is a set of extended context-free grammatical rules such as outlined in "Iwanami Koza, Zyoho Kagaku 23: Kazu to Shiki to Bun no Shori", Chapter 5 'Kikai Honyaku', Iwanami Shoten".
  • the terminology dictionary 26 also has a format as outlined in the above described article. This format is shown in Fig. 7. To eliminate ambiguities in the meaning of a word, a semantic ID is given to each word. The semantic ID helps to associate the input term or words with term or words that are understandable to the database 9 (Fig. 6). For example, since there is no retrieval key for "shoohin” (commodity), "shoohin mei” (commodity name) is designated as the semantic ID for "shoohin”.
  • the database 9 (Fig. 6) includes information regarding the commodity name. Analogously, since there is no entry for "choko rui” (chocolates and the like) in the database, “chokoreeto rui” (chocolates and the like) is designated as its semantic ID.
  • Each entry in the terminology dictionary 26 also includes a semantic marker.
  • the semantic marker is provided to connect an ambiguous word (i.e., not directly defined in the virtual table) to a correspondence attribute. Further, the semantic marker serves to combine words that are identical under the semantic restriction in the virtual table. For example, since there are no such retrieval keys for "sengetsu" (last month) in the virtual table 28 (Fig. 6), the semantic marker for this term is month (date), hence, indicating that this term is an indication of date on a monthly basis. Similarly, the term “Kyonen (last year), "hi” (day) and “toshi” (year) are also assigned semantic markers that indicate that the terms refer to date.
  • a plurality of semantic markers may be allowed for a word (e.g. "uriage” in Fig. 7).
  • the item in the virtual table 28 (Fig. 6) that is capable of corresponding to a retrieval key of the database 9 is searched by following semantic restriction on the virtual table designated by the semantic marker.
  • a column for corresponding items e.g. the "ITEM” column in Fig. 7 is provided for designating which one of the tables of the virtual table 28 (Fig. 6) should be referenced.
  • a correspondence attribute is determined by the modifying-modified relation thereof or a semantic marker for units of numerical values.
  • an actual value is determined in accordance with the definition of an entity table.
  • the construction of the query is identified and the object of the interrogation is known. It is necessary to conform the object of interrogation to an item possessed by the database. While several methods may be employed for this purpose, the most effective method is one in which the virtual table is provided to associate similar meanings which are referenced as different words in the database. By providing a virtual table, alteration and/or addition of the system is easy compared to a method in which the retrieval object item of the database is directly entered into a terminology dictionary. Further, a variety of different natural Japanese queries may be correctly processed and the queries may employ various different modifier representations.
  • the parser 22 (Fig. 6), thus, produces a hierarchical syntax tree like that shown in Fig. 9. This result indicates that the sales (i.e. "uriage") are what is sought.
  • the term "Chokoreeto rui” (chocolate and the like) specifies the commodity group for which sales are sought, and the term “sengetsu” (last month) indicates the time frame for which the sales data is sought.
  • This syntax tree is passed to the collating unit as the syntax analysis result (see step 40 in Fig. 10).
  • the syntax tree is not directly converted into a database retrieving logic formula, but rather is converted into an intermediate representation known as a virtual table logic formula. Then an appropriate table in the virtual table 28 (Fig. 6) is selected (step 42 in Fig. 10).
  • the terminology dictionary 26 (Fig. 7) is referenced.
  • the "item” field is examined for "sengetsu” (last month).
  • the item field points to Table 5 in the virtual table 28 (Fig. 6).
  • Table 5 (Fig. 8c) in the virtual table 28 (Fig. 6) is examined.
  • the entry for "sengetsu” has a correspondence attribute pointing to Definition Table B-21. Accordingly, the entry with argument 21 in Definition Table B is examined (see Fig. 11a).
  • This table entry sets forth the method of calculation for "sengetsu”.
  • "sengetsu" (the last month) is a value which varies according to the point in time of input and, therefore, must be calculated.
  • the current data is an 8 decimal digit number with digits 8-5 holding the year (e.g. "1992"), digits 4 and 3 holding the month (e.g. "07", for July) and bits 2 and 1 holding the date (e.g. "11").
  • an example format for the date of July 11, 1992 is "19920711”.
  • the Definition Table B tells the system how to calculate the last month (i.e. June or "06"). First one is subtracted from the month digits 4 and 3. Hence, a result of (07-1) or 06 is obtained. Then, the system checks whether the result is 00. In this case, the result is not zero. If the result of the subtraction is 00, it is an indication that the last month was December of the previous year. Therefore, the month digits 4 and 3 are replaced with the digit 12 for December, and the year digits 8-5 (the high order digits) are decremented by one. Lastly, the day digits 1 and 2 are replaced with 00.
  • a table in the virtual table 28 (Fig. 6) for "sengetsu” (last month) is selected.
  • a plurality of virtual tables are designated for "chokoreeto rui” (chocolates and the like). Specifically, Tables 1 and 3 are designated.
  • An entry in the terminology dictionary 28 is also examined for the term “uriage” (sales). The entry for "uriage” (sales) designates Table 1. Given that both the entry for "Chokoreeto rui" and the entry for "uriage” specify Table 1 of the virtual table 28, Table 1 is selected.
  • an intermediate representation is formed by the collating process (step 44 in Fig. 10) performed by the collating unit 30.
  • the collating unit 30 internally comprises: a virtual table selection unit 60, for selecting a table in the virtual table 28 (Fig. 6); an actual value calculation/combination unit 62 (Fig. 14) for performing calculations and combination; and an interrogative structure determining unit 64 for determining the structure of interrogations that are passed to the database formula generation unit 32.
  • the collating process involves incorporating the contents of a dictionary referenced by the input natural language query into the table of the virtual table that was selected at step 42 in Fig. 14 or by performing attribute coupling between virtual tables.
  • two virtual tables have been selected: Table 1 (by the entries in the terminology dictionary for "uriage” and “Chokoreeto rui") and Table 5 (by the entry for "sengetsu”).
  • a natural language correspondence logic formula 50 is generated as shown in Fig. 12.
  • the correspondence logic formula 50 is a table that sets forth what information is known from the query and what additional information is needed to complete the query. Specifically, it sets forth the relevant variables and any values of these variables that are known.
  • step 46 of Fig. 10 a necessary virtual table is added to access the database 9 (Fig. 6).
  • table 3 (Fig. 8b) of the virtual table 28 (Fig. 6) is selected based on correspondence attribute of "shoohin gun mei" 7 (commodity group name) in table 1 (Fig. 8a), which specifies Table 3-2.
  • the entry in table 3 directs the user to Database Table entry 3-2 (e.g. DB 3-2).
  • the actual value of "sengetsu" (last month) is calculated from the Definition Table B (as was discussed above).
  • the table, thus, provided is indicated by 52 in Fig. 13.
  • the data shown assumes that the current date is in May 1990. Hence, the last month is April 1990 or "19900400".
  • the commodity group code serves as the attribute for connecting Table 1 and the commodity group master table, and it possesses "Code" as an undetermined variable.
  • This table 52 is converted into a database retrieval formula by the database formula generation unit 32 (Fig. 6) at step 48 (Fig. 10). Retrievals are performed sequentially by the retrieval unit 34 (Fig. 6) based on the retrieval formula to fill the undetermined variables in the table 52 (Fig. 13).
  • the undetermined variable "Code" is determined from commodity group master table 19 (i.e., table C in Fig. 3c) to be 200, which corresponds to "chokoreeto rui" (chocolates and the like).
  • the query must be converted into a query set forth in a database retrieval language to retrieve data from the database.
  • a database retrieval language To replace the structure of the Japanese natural language query with database retrieval formulas, it is necessary to put together the restrictions and grammar possessed by the database retrieval language in the terminology definition table 26 (Fig. 6). Construction of the queries in the database retrieval language are made by referring to this terminology definition table as described above. Further, having a separate grammar definition table 24 produces the advantage that all the changes to the database retrieval language may be absorbed by the grammar definition table, even when the present invention is applied to a system using a different database retrieval language.
  • a database is designated and a conversion is made into a retrieval logic formula which is suitable even when an ambiguous word is included in the query or an omission occurs in the input query.
  • the collating unit can designate a highly probable database file by selecting a suitable virtual table even for an ambiguous input query.
  • the term "sengetsu” (last month) was included in the natural language query. This term was an ambiguous word related to time.
  • the system also has the capability of properly analyzing other ambiguous terms relating to time.
  • the Japanese input sentence is "Kotoshi no haru no uriage ha" (Sale for the spring of this year?).
  • the parser 22 (Fig. 6) decomposes this sentence into its constituent part "uriage” (sales) and “kotoshi no haru” (the spring of this year). Further, the parser 22 knows that "kotoshi no haru” modifies "uriage”.
  • the parser 22 looks up the term "kotoshi no haru” in the terminology dictionary 26 and is directed to an appropriate table in the virtual table 28.
  • the entry in the virtual table directs the user to entry 3 in Definition Table A as shown in Fig. 15. This entry indicates that spring extends from 03/01 to 05/31.
  • the word "kotoshi no haru” (the spring of this year) contained in the syntax analysis result is replaced by "1990 nen 3 gatsu 1 nichi - 1990 nen 5 gatsu 31 nichi” (March 1 1990 - May 31 1990).
  • any combination of time words to be used must be recorded on a terminology dictionary as a single word.
  • “kotoshi” (this year) and “haru” (spring) be combined “kotoshi no haru” (the spring of this year)
  • a terminology dictionary must be prepared for each user.
  • an alternative embodiment as shown in Figs. 16a and 16b may be employed.
  • This alternative embodiment differs from the first embodiment in that it includes: a point in time calculation unit 70, for calculating a specific point in time from the current date, a time interval definition table reference unit 80, and a combining unit 82 for adding the reference result of the time interval definition table reference unit 80 and the calculated result of a point in time. Further, a system timer 68 is provided.
  • a syntax analysis result 72 i.e., a syntax tree
  • the syntax analysis result contains "sakunen” (last year) and "fuyu” (winter), which are time words.
  • the definition of the word "sakunen” (the last year) is obtained by time calculation, and the definition of the word “fuyu” (winter) is designated to be described in the time interval definition table 82 (Fig. 16b).
  • the syntax analysis result 72 is passed to the collating unit 30, where the result is received by the point in time calculation unit 70.
  • a point in time calculation is performed with respect to the current date (e.g., "19901224") that is obtained by a system timer 68.
  • the actual calculation method performed is selected from the definition provided in Definition Table B in Fig. 11. The definition that is chosen depends on the value in the argument column in the terminology dictionary.
  • an 8-digit integer value indicating the year “sakunen” (last year), "19890000”, is obtained from the calculation method, corresponding to the value "11" in the argument column of "sakunen” (the last year), which states, "Subtract 1 from the four high order digits and replace the four low order digits with "0000". Subsequently, the calculated integer value is substituted for the portion of "sakunen” (the last year) in the syntax analysis result 72 to obtain a point in time calculation result 74.
  • the time interval definition reference unit 80 contains the actual dates corresponding to "fuyu” (winter). It obtains these dates by referring the time interval definition table 84. Hence, as shown in Fig. 15, “fuyu” is defined as starting at "00001201” (i.e., December 1) and ending at "00010331” i.e., March 31 of the next year).
  • the time interval definition table reference unit 80 substitutes the retrieved value 86 for "fuyu" (winter) in the point in time calculation result 24 to obtain a time interval definition table reference result 76.
  • the combining unit 82 combines the actual dates corresponding to "sakunen” (the last year) and "fuyu” (winter) by addition to obtain a complete 8 digit range for dates for the interval as shown in the calculation result 78. Specifically, the year “19890000” is added to the dates of "fuyu” "00001201” - “00010331” to obtain “19891201” - "19900331”. The calculation result "19891201-19900331" means "from December 1, 1989 to March 31, 1990". The calculation result 78 is then processed as discussed in the first embodiment.
  • the user may obtain a calculation result in accordance with definition without altering the terminology dictionary 26 (Fig. 16a). That is, it is possible for users to share a terminology dictionary and manage the time interval definition table individually. This benefit of sharing a terminology dictionary is more apparent when it is appreciated that a terminology dictionary is large in size and amendment of a terminology dictionary is difficult. Moreover, if words containing many modifiers are to be defined, storage requirements are large. Hence, providing a separate terminology dictionary for every user is cumbersome.
  • the example input natural language queries 1 (Fig. 6) and 66 (Fig. 16a) requested sales information that could be readily reproduced by the system.
  • the system is capable of handling more sophisticated queries that require reasoning. For example, suppose that the Japanese input query is a sentence "Sengetsu no uriage yori kongetsu no uriage ga ooi tokuisaki ha" (What customer had more sales in this month than sales in the last month?).
  • the system produces a retrieving logic formula, also known as the entity table logic formula 14, in the form 140 shown in Fig. 17a.
  • the formula 140 includes a result table 142 for storing the final results of the retrieved data.
  • the result table 142 includes a location for storing the customer's name and tables for storing the total sales of this month and the total sales of last month.
  • the entity table logic formula 140 includes a GT table, which is a table in the virtual table that performs a logical operation on parameters to determine if one parameter (the left side) is greater than the other (the right side).
  • the total sales of the last month table includes a pointer pointing to a last month's intermediate result table 144 that holds the results of intermediate calculations that are necessary to determine the total sales of the last month. Similarly, the total sales of this month's table points to this month's intermediate result table 146. Both of the intermediate result tables 144 and 146 seek to have information regarding the customer code and the total sales for their respective months. In order to calculate the total sales of the last month, it is necessary to determine the calculation object (i.e., what kind of information is being sought). In addition, it is necessary to determine the amount of orders that were received during the month from that customer. Accordingly, there is an additional table, the total sales of the last month's intermediate result table 148.
  • a total sales in this month's intermediate result table 151 that seeks similar information for this month's sale, is also provided.
  • the amount of received order for this month and last month for the specified customer code are requested and passed to the database formula generation unit 32 which converts the logic formula into a database retrieval formula 157 using the database retrieval word grammar definition table 155.
  • the result table and the various intermediate result tables 144, 146, 148 and 151 are passed to the database formula generation unit 32.
  • equality tables (denoted as EQ tables) are passed to the database formula generation unit 32.
  • EQ Tables 3 and 4 are passed to the database formula generation unit 32, EQ Table 3 seeks to determine if the received order file date is equal to the last month date, and EQ Table 4 seeks to determine if the received order file date is equal to today's date.
  • the entity table logic formula 140 is processed by the database formula generation unit 32 (Fig. 17c) which uses the database retrieval word grammar definition table to process the logic formula 140.
  • the database retrieval word grammar definition table is examined by the database formula generation unit 32 with respect to the retrieval logic formula 140.
  • the database retrieval word definition table initially processes result table as indicated in Fig. 18. In particular, the system is directed to select the SELECT (item) FROM (reference table) WHERE (condition). Thus, the result table is converted into a database retrieval formula of ⁇ interrogation 3> of Fig. 19.
  • the retrieval word grammar definition table 155 has a similar entry for the intermediate result tables 144 and 146. Further, the database formula generation unit 32 investigates the executing order of the specified operations with respect to another.
  • the system proceeds to process each of the interrogations as indicated in Fig. 19.
  • interrogation 1 which is interrogation for the last month's intermediate result table
  • the customer table in the database 9 (Fig. 17c) is retrieved using retrieval unit 34 to obtain the customer code information.
  • the system seeks to sum the amount fields in the received order file of the database 9. In order to perform this calculation, the system sums the amount entries having the appropriate customer code and which meet the date limitations of last month.
  • the EQ table 3 is used to ensure that the date requirements are fulfilled. In this fashion, the intermediate result table is filled in with the relevant information.
  • Interrogation 2 involves the processing for this month's intermediate result table.
  • the processing is the same as interrogation 1 except that different date requirements are utilized. Specifically, the date must correspond to the limitations for this month. In this fashion, the information for this month's intermediate result table is completed.
  • interrogation 3 is processed.
  • the interrogation 3 is the interrogation for the result table.
  • Fig. 19 indicates, the customer table in the database customer and name are selected, as are the total sales of this last month table and the total sales of this month table. This information is retrieved from the customer table in the database 9 (Fig. 17c) and from the last month's intermediate result table 144 (Fig. 17b) and this month's intermediate result table 146.
  • the sales of this month table must be greater than the sales of last month table and the customer code of this month's intermediate result table must equal the customer table and code.
  • this approach provides the additional advantage a plurality of sequenced data retrievals are possible by way of intermediate results.
  • the system also provides the advantage that it is possible to readily conform to a different database retrieval language by altering the grammar definition table.
  • the database retrieval formula for a new retrieval language may be generated and an extensive rewriting thereof is not necessary. Rather, a simple change in the description of (item), (reference table), (condition) or SELECT, FROM, WHERE of the designated item to the result table of the grammar definition table is all that is required.
  • Figs. 20a and 20b are helpful in explaining the structure of a syntax tree that is produced for an input query which requires a plurality of logic formula groups.
  • the input sentence is broken down by the parser 22 (Fig.
  • Fig. 20a shows the syntax tree for the first example query
  • Fig. 20b shows the syntax tree for the second example query.
  • Particles are detected and the elements are forcibly divided at the parser 22 (Fig. 6).
  • "ji" refers to a word serving as a key
  • "fu" is a modifier.
  • the modifier is used to refer to the surface restriction or is regarded as a special modifier in searching the virtual table.
  • the first example query seek to compare sales of two entities. As such, two tables have to be selected. If a table is selected so that a comparison cannot be made. Two tables can be selected by dividing the syntax tree into groups.
  • a virtual table (see Fig. 21a) corresponding to a comparison expression like the "ooi hyo" shown in Fig. 20a is provided and a virtual table logic formula for comparison is generated by indicating the relation between the two tables with the comparison virtual table.
  • the comparison virtual table can be used for converting a word indicating a comparison meaning in any language to an expression such as, [GT] (greater than).
  • the two virtual table logic formulas are set by Group (a) in Fig. 20a.
  • interrogatives may be dealt with to some extent by providing an item for surface restriction in the virtual table and by investigating the items relative to the surface restriction. For example, with respect to an input sentence "Nani wo uttaka” (What was sold?), since only a commodity name or commodity group name falls under those with the surface restriction "wo" in “uru hyo”, it is possible to assume that "nani” (what) refers to one of them.
  • a response format selection unit may be provided in the retrieval unit. This unit should provide at least two types of formats, i.e., a tabular format and sentence format, as the outputting format.
  • system may be adjusted to operate on natural language queries that are formulated in languages other than Japanese. Further, the system may be implemented on data processing system other than that shown in Fig. 2.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
EP92111820A 1991-07-11 1992-07-10 Datenbankauffindungssystem zur Beantwortung natursprachlicher Fragen mit dazugehörigen Tabellen Expired - Lifetime EP0522591B1 (de)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
JP17121791 1991-07-11
JP3171217A JP2596260B2 (ja) 1990-07-18 1991-07-11 対応表使用データベース検索装置
JP171217/91 1991-07-11

Publications (3)

Publication Number Publication Date
EP0522591A2 true EP0522591A2 (de) 1993-01-13
EP0522591A3 EP0522591A3 (en) 1993-11-03
EP0522591B1 EP0522591B1 (de) 2000-03-22

Family

ID=15919214

Family Applications (1)

Application Number Title Priority Date Filing Date
EP92111820A Expired - Lifetime EP0522591B1 (de) 1991-07-11 1992-07-10 Datenbankauffindungssystem zur Beantwortung natursprachlicher Fragen mit dazugehörigen Tabellen

Country Status (3)

Country Link
US (1) US5442780A (de)
EP (1) EP0522591B1 (de)
DE (1) DE69230814T2 (de)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0585079A1 (de) * 1992-08-21 1994-03-02 Canon Kabushiki Kaisha Verfahren und Vorrichtung zur Verarbeitung von Signalen
US5495604A (en) * 1993-08-25 1996-02-27 Asymetrix Corporation Method and apparatus for the modeling and query of database structures using natural language-like constructs
WO2000007117A3 (en) * 1998-07-30 2000-05-18 British Telecomm An index to a semi-structured database
US6202064B1 (en) 1997-06-20 2001-03-13 Xerox Corporation Linguistic search system
DE19952769A1 (de) * 1999-11-02 2001-05-03 Sap Ag System und Verfahren zum Abrufen von Informationen mit Abfragen in natürlicher Sprache
GB2358937A (en) * 1999-09-03 2001-08-08 Ibm Hierarchical translation of a natural language statement to a formal command in a computer system
WO2001040989A3 (de) * 1999-10-28 2002-07-18 Kiwilogic Com Ag Verfahren zur erweiterung einer datenbank bestehend aus datenpaaren aus einander zugeordneter erkennung und antwort
WO2002010981A3 (en) * 2000-07-28 2003-12-31 Easyask Inc Distributed search system and method
WO2004012066A3 (en) * 2002-07-29 2004-07-29 Electronic Data Syst Corp Interactive natural language query processing system and method
US7246116B2 (en) * 2004-04-22 2007-07-17 International Business Machines Corporation Method, system and article of manufacturing for converting data values quantified using a first measurement unit into equivalent data values when quantified using a second measurement unit in order to receive query results including data values measured using at least one of the first and second measurement units
WO2007044434A3 (en) * 2005-10-05 2007-07-26 Piper Communications Inc Systems and methods for electronic searching of automotive parts database
US7362075B2 (en) 2004-06-08 2008-04-22 Friwo Geraetebau Gmbh Battery charger with charge state detection on the primary side
CN106021232A (zh) * 2016-05-24 2016-10-12 北京工商大学 一种基于依存句法关系的微博马甲账号识别方法

Families Citing this family (194)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5434777A (en) * 1992-05-27 1995-07-18 Apple Computer, Inc. Method and apparatus for processing natural language
JP3476237B2 (ja) * 1993-12-28 2003-12-10 富士通株式会社 構文解析装置
US5748841A (en) * 1994-02-25 1998-05-05 Morin; Philippe Supervised contextual language acquisition system
US5748974A (en) * 1994-12-13 1998-05-05 International Business Machines Corporation Multimodal natural language interface for cross-application tasks
JP3571408B2 (ja) * 1995-03-31 2004-09-29 株式会社日立製作所 文書加工方法および装置
US5887120A (en) 1995-05-31 1999-03-23 Oracle Corporation Method and apparatus for determining theme for discourse
US5694523A (en) * 1995-05-31 1997-12-02 Oracle Corporation Content processing system for discourse
US5899989A (en) * 1996-05-14 1999-05-04 Sharp Kabushiki Kaisha On-demand interface device
US5909677A (en) 1996-06-18 1999-06-01 Digital Equipment Corporation Method for determining the resemblance of documents
US5924089A (en) * 1996-09-03 1999-07-13 International Business Machines Corporation Natural language translation of an SQL query
US6085162A (en) * 1996-10-18 2000-07-04 Gedanken Corporation Translation system and method in which words are translated by a specialized dictionary and then a general dictionary
US5836771A (en) 1996-12-02 1998-11-17 Ho; Chi Fai Learning method and system based on questioning
US6272495B1 (en) * 1997-04-22 2001-08-07 Greg Hetherington Method and apparatus for processing free-format data
US6460034B1 (en) 1997-05-21 2002-10-01 Oracle Corporation Document knowledge base research and retrieval system
US6038560A (en) * 1997-05-21 2000-03-14 Oracle Corporation Concept knowledge base search and retrieval system
US5940821A (en) * 1997-05-21 1999-08-17 Oracle Corporation Information presentation in a knowledge base search and retrieval system
US6230154B1 (en) * 1997-07-15 2001-05-08 Morphometrix Technologies Inc. Database element retrieval by example
US5895466A (en) * 1997-08-19 1999-04-20 At&T Corp Automated natural language understanding customer service system
US6119087A (en) * 1998-03-13 2000-09-12 Nuance Communications System architecture for and method of voice processing
JPH11327879A (ja) * 1998-05-15 1999-11-30 Fujitsu Ltd 変数検索装置及び方法並びに変数検索プログラムを記録したコンピュータ読取り可能な記録媒体
US6219643B1 (en) 1998-06-26 2001-04-17 Nuance Communications, Inc. Method of analyzing dialogs in a natural language speech recognition system
US7082397B2 (en) 1998-12-01 2006-07-25 Nuance Communications, Inc. System for and method of creating and browsing a voice web
US7263489B2 (en) 1998-12-01 2007-08-28 Nuance Communications, Inc. Detection of characteristics of human-machine interactions for dialog customization and analysis
US6748374B1 (en) * 1998-12-07 2004-06-08 Oracle International Corporation Method for generating a relational database query statement using one or more templates corresponding to search conditions in an expression tree
US7801913B2 (en) * 1998-12-07 2010-09-21 Oracle International Corporation System and method for querying data for implicit hierarchies
US6587856B1 (en) 1998-12-07 2003-07-01 Oracle International Corporation Method and system for representing and accessing object-oriented data in a relational database system
US6233556B1 (en) 1998-12-16 2001-05-15 Nuance Communications Voice processing and verification system
US6430531B1 (en) 1999-02-04 2002-08-06 Soliloquy, Inc. Bilateral speech system
US6513027B1 (en) * 1999-03-16 2003-01-28 Oracle Corporation Automated category discovery for a terminological knowledge base
US6584464B1 (en) 1999-03-19 2003-06-24 Ask Jeeves, Inc. Grammar template query system
US7143042B1 (en) 1999-10-04 2006-11-28 Nuance Communications Tool for graphically defining dialog flows and for establishing operational links between speech applications and hypermedia content in an interactive voice response environment
US6665666B1 (en) * 1999-10-26 2003-12-16 International Business Machines Corporation System, method and program product for answering questions using a search engine
US6615223B1 (en) 2000-02-29 2003-09-02 Oracle International Corporation Method and system for data replication
US8645137B2 (en) 2000-03-16 2014-02-04 Apple Inc. Fast, language-independent method for user authentication by voice
JP2001325252A (ja) * 2000-05-12 2001-11-22 Sony Corp 携帯端末及びその情報入力方法、辞書検索装置及び方法、媒体
US20020152202A1 (en) * 2000-08-30 2002-10-17 Perro David J. Method and system for retrieving information using natural language queries
US6461166B1 (en) 2000-10-17 2002-10-08 Dennis Ray Berman Learning system with learner-constructed response based testing methodology
US7957986B1 (en) 2001-04-09 2011-06-07 Trover Solutions, Inc. System and method for managing account processing
US20030004706A1 (en) * 2001-06-27 2003-01-02 Yale Thomas W. Natural language processing system and method for knowledge management
US7191337B2 (en) * 2001-06-30 2007-03-13 International Business Machines Corporation Apparatus for wildcarded security policy and method therefor
US7074128B2 (en) 2001-08-03 2006-07-11 Drb Lit Ltd. Method and system for enhancing memorization by using a mnemonic display
JP2003271389A (ja) * 2002-03-19 2003-09-26 Shuichi Araki 自然言語によるソフトウェア・オブジェクトの操作方法及びそのためのプログラム
US7840422B1 (en) 2002-04-09 2010-11-23 Trover Solutions, Inc. Systems and methods for managing insurance claims
US7574427B2 (en) * 2002-05-17 2009-08-11 Delefevre Patrick Y Neutral sales consultant
US20040167875A1 (en) * 2003-02-20 2004-08-26 Eriks Sneiders Information processing method and system
US7357640B2 (en) * 2003-07-02 2008-04-15 Drb Lit Ltd. Lock-In Training system
TWM249950U (en) * 2004-01-02 2004-11-11 Cvc Technologies Inc Cap tightening machine capable of controlling tightening torque
JP2005242416A (ja) * 2004-02-24 2005-09-08 Shogakukan Inc 自然言語文の検索方法および検索装置
CN101228521B (zh) * 2004-03-15 2013-02-13 雅虎公司 用于将用户门户页面订阅到聚合馈信的系统和方法
US7364432B2 (en) * 2004-03-31 2008-04-29 Drb Lit Ltd. Methods of selecting Lock-In Training courses and sessions
US7925658B2 (en) * 2004-09-17 2011-04-12 Actuate Corporation Methods and apparatus for mapping a hierarchical data structure to a flat data structure for use in generating a report
US9390132B1 (en) 2009-10-16 2016-07-12 Iqor Holdings, Inc. Apparatuses, methods and systems for a universal data librarian
US9405800B1 (en) 2004-12-13 2016-08-02 Iqor Holdings Inc. Apparatuses, methods and systems for a universal payment integrator
US7644021B2 (en) * 2005-02-10 2010-01-05 The Kroger Co. Electronically assisted enterprise journal system
US8046348B1 (en) 2005-06-10 2011-10-25 NetBase Solutions, Inc. Method and apparatus for concept-based searching of natural language discourse
US8677377B2 (en) 2005-09-08 2014-03-18 Apple Inc. Method and apparatus for building an intelligent automated assistant
US9318108B2 (en) 2010-01-18 2016-04-19 Apple Inc. Intelligent automated assistant
US20080104257A1 (en) * 2006-10-26 2008-05-01 Yahoo! Inc. System and method using a refresh policy for incremental updating of web pages
US8745183B2 (en) * 2006-10-26 2014-06-03 Yahoo! Inc. System and method for adaptively refreshing a web page
US20080104502A1 (en) * 2006-10-26 2008-05-01 Yahoo! Inc. System and method for providing a change profile of a web page
US8977255B2 (en) 2007-04-03 2015-03-10 Apple Inc. Method and system for operating a multi-function portable electronic device using voice-activation
US8131740B2 (en) * 2007-10-09 2012-03-06 International Business Machines Corporation User-specific search indexing within a virtual environment
US9330720B2 (en) 2008-01-03 2016-05-03 Apple Inc. Methods and apparatus for altering audio output signals
JP5159375B2 (ja) 2008-03-07 2013-03-06 インターナショナル・ビジネス・マシーンズ・コーポレーション メタバースにおけるオブジェクトの真贋判断システム、方法及びそのコンピュータ・プログラム
US8996376B2 (en) 2008-04-05 2015-03-31 Apple Inc. Intelligent text-to-speech conversion
US10496753B2 (en) 2010-01-18 2019-12-03 Apple Inc. Automatically adapting user interfaces for hands-free interaction
US20100030549A1 (en) 2008-07-31 2010-02-04 Lee Michael M Mobile device having human language translation capability with positional feedback
WO2010067118A1 (en) 2008-12-11 2010-06-17 Novauris Technologies Limited Speech recognition involving a mobile device
US8095524B2 (en) * 2009-03-18 2012-01-10 International Business Machines Corporation Method and system for integrating personal information search and interaction on web/desktop applications
US9858925B2 (en) 2009-06-05 2018-01-02 Apple Inc. Using context information to facilitate processing of commands in a virtual assistant
US10241752B2 (en) 2011-09-30 2019-03-26 Apple Inc. Interface for a virtual digital assistant
US10706373B2 (en) 2011-06-03 2020-07-07 Apple Inc. Performing actions associated with task items that represent tasks to perform
US10241644B2 (en) 2011-06-03 2019-03-26 Apple Inc. Actionable reminder entries
US9431006B2 (en) 2009-07-02 2016-08-30 Apple Inc. Methods and apparatuses for automatic speech recognition
US9454576B1 (en) 2009-10-16 2016-09-27 Iqor Holdings Inc., Iqor US Inc. Apparatuses, methods and systems for an employee onboarding automator
US9405799B1 (en) 2009-10-16 2016-08-02 Iqor Holdings, Inc. Apparatuses, methods and systems for an employee referral facilitator
US9053146B1 (en) 2009-10-16 2015-06-09 Iqor U.S. Inc. Apparatuses, methods and systems for a web access manager
US9063978B1 (en) 2009-10-16 2015-06-23 Igor US Inc. Apparatuses, methods and systems for a financial transaction tagger
US9396232B1 (en) 2009-10-16 2016-07-19 Iqor Holdings, Inc. Apparatuses, methods and systems for a rule-integrated virtual punch clock
US9043355B1 (en) 2009-10-16 2015-05-26 Iqor U.S. Inc. Apparatuses, methods and systems for a journal entry automator
US9098509B1 (en) 2009-10-16 2015-08-04 Iqor Holding Inc., Igor U.S. Inc. Apparatuses, methods and systems for a call restrictor
US9672281B1 (en) 2009-10-16 2017-06-06 Iqor US. Inc. Apparatuses, methods and systems for a call searcher
US9454577B1 (en) 2009-10-16 2016-09-27 Iqor Holdings Inc, Iqor US Inc. Apparatuses, methods and systems for an employee reimbursement evaluator
US8812482B1 (en) 2009-10-16 2014-08-19 Vikas Kapoor Apparatuses, methods and systems for a data translator
US10553209B2 (en) 2010-01-18 2020-02-04 Apple Inc. Systems and methods for hands-free notification summaries
US10679605B2 (en) 2010-01-18 2020-06-09 Apple Inc. Hands-free list-reading by intelligent automated assistant
US10276170B2 (en) 2010-01-18 2019-04-30 Apple Inc. Intelligent automated assistant
US10705794B2 (en) 2010-01-18 2020-07-07 Apple Inc. Automatically adapting user interfaces for hands-free interaction
WO2011102246A1 (ja) 2010-02-18 2011-08-25 株式会社ニコン 情報処理装置、携帯型装置及び情報処理システム
US8682667B2 (en) 2010-02-25 2014-03-25 Apple Inc. User profiling for selecting user specific voice input processing information
US8346775B2 (en) 2010-08-31 2013-01-01 International Business Machines Corporation Managing information
US10762293B2 (en) 2010-12-22 2020-09-01 Apple Inc. Using parts-of-speech tagging and named entity recognition for spelling correction
US9262612B2 (en) 2011-03-21 2016-02-16 Apple Inc. Device access using voice authentication
US9280535B2 (en) 2011-03-31 2016-03-08 Infosys Limited Natural language querying with cascaded conditional random fields
US10057736B2 (en) 2011-06-03 2018-08-21 Apple Inc. Active transport based notifications
US8994660B2 (en) 2011-08-29 2015-03-31 Apple Inc. Text correction processing
US10134385B2 (en) 2012-03-02 2018-11-20 Apple Inc. Systems and methods for name pronunciation
US9483461B2 (en) 2012-03-06 2016-11-01 Apple Inc. Handling speech synthesis of content for multiple languages
US9280610B2 (en) 2012-05-14 2016-03-08 Apple Inc. Crowd sourcing information to fulfill user requests
US9721563B2 (en) 2012-06-08 2017-08-01 Apple Inc. Name recognition system
US9495129B2 (en) 2012-06-29 2016-11-15 Apple Inc. Device, method, and user interface for voice-activated navigation and browsing of a document
US10430406B2 (en) * 2012-08-13 2019-10-01 Aria Solutions, Inc. Enhanced high performance real-time relational database system and methods for using same
US9576574B2 (en) 2012-09-10 2017-02-21 Apple Inc. Context-sensitive handling of interruptions by intelligent digital assistant
US9547647B2 (en) 2012-09-19 2017-01-17 Apple Inc. Voice-based media searching
US20140143254A1 (en) * 2012-11-16 2014-05-22 Ritendra Datta Category and Attribute Specifications for Product Search Queries
US10394816B2 (en) 2012-12-27 2019-08-27 Google Llc Detecting product lines within product search queries
KR102579086B1 (ko) 2013-02-07 2023-09-15 애플 인크. 디지털 어시스턴트를 위한 음성 트리거
US9368114B2 (en) 2013-03-14 2016-06-14 Apple Inc. Context-sensitive handling of interruptions
WO2014144579A1 (en) 2013-03-15 2014-09-18 Apple Inc. System and method for updating an adaptive speech recognition model
KR101759009B1 (ko) 2013-03-15 2017-07-17 애플 인크. 적어도 부분적인 보이스 커맨드 시스템을 트레이닝시키는 것
WO2014197334A2 (en) 2013-06-07 2014-12-11 Apple Inc. System and method for user-specified pronunciation of words for speech synthesis and recognition
WO2014197336A1 (en) 2013-06-07 2014-12-11 Apple Inc. System and method for detecting errors in interactions with a voice-based digital assistant
US9582608B2 (en) 2013-06-07 2017-02-28 Apple Inc. Unified ranking with entropy-weighted information for phrase-based semantic auto-completion
WO2014197335A1 (en) 2013-06-08 2014-12-11 Apple Inc. Interpreting and acting upon commands that involve sharing information with remote devices
JP6259911B2 (ja) 2013-06-09 2018-01-10 アップル インコーポレイテッド デジタルアシスタントの２つ以上のインスタンスにわたる会話持続を可能にするための機器、方法、及びグラフィカルユーザインタフェース
US10176167B2 (en) 2013-06-09 2019-01-08 Apple Inc. System and method for inferring user intent from speech inputs
HK1220313A1 (zh) 2013-06-13 2017-04-28 苹果公司 用於由语音命令发起的紧急呼叫的系统和方法
CN105453026A (zh) 2013-08-06 2016-03-30 苹果公司 基于来自远程设备的活动自动激活智能响应
US9606977B2 (en) * 2014-01-22 2017-03-28 Google Inc. Identifying tasks in messages
US9620105B2 (en) 2014-05-15 2017-04-11 Apple Inc. Analyzing audio input for efficient speech and music recognition
US10592095B2 (en) 2014-05-23 2020-03-17 Apple Inc. Instantaneous speaking of content on touch devices
US9502031B2 (en) 2014-05-27 2016-11-22 Apple Inc. Method for supporting dynamic grammars in WFST-based ASR
US10289433B2 (en) 2014-05-30 2019-05-14 Apple Inc. Domain specific language for encoding assistant dialog
US9785630B2 (en) 2014-05-30 2017-10-10 Apple Inc. Text prediction using combined word N-gram and unigram language models
US9842101B2 (en) 2014-05-30 2017-12-12 Apple Inc. Predictive conversion of language input
US9734193B2 (en) 2014-05-30 2017-08-15 Apple Inc. Determining domain salience ranking from ambiguous words in natural speech
US9430463B2 (en) 2014-05-30 2016-08-30 Apple Inc. Exemplar-based natural language processing
US9633004B2 (en) 2014-05-30 2017-04-25 Apple Inc. Better resolution when referencing to concepts
EP3480811A1 (de) 2014-05-30 2019-05-08 Apple Inc. Verfahren zur eingabe von mehreren befehlen mit einer einzigen äusserung
US9760559B2 (en) 2014-05-30 2017-09-12 Apple Inc. Predictive text input
US10078631B2 (en) 2014-05-30 2018-09-18 Apple Inc. Entropy-guided text prediction using combined word and character n-gram language models
US9715875B2 (en) 2014-05-30 2017-07-25 Apple Inc. Reducing the need for manual start/end-pointing and trigger phrases
US10170123B2 (en) 2014-05-30 2019-01-01 Apple Inc. Intelligent assistant for home automation
US9460075B2 (en) 2014-06-17 2016-10-04 International Business Machines Corporation Solving and answering arithmetic and algebraic problems using natural language processing
US10659851B2 (en) 2014-06-30 2020-05-19 Apple Inc. Real-time digital assistant knowledge updates
US9338493B2 (en) 2014-06-30 2016-05-10 Apple Inc. Intelligent automated assistant for TV user interactions
US9514185B2 (en) * 2014-08-07 2016-12-06 International Business Machines Corporation Answering time-sensitive questions
US10446141B2 (en) 2014-08-28 2019-10-15 Apple Inc. Automatic speech recognition based on user feedback
US9818400B2 (en) 2014-09-11 2017-11-14 Apple Inc. Method and apparatus for discovering trending terms in speech requests
US10789041B2 (en) 2014-09-12 2020-09-29 Apple Inc. Dynamic thresholds for always listening speech trigger
US9430557B2 (en) * 2014-09-17 2016-08-30 International Business Machines Corporation Automatic data interpretation and answering analytical questions with tables and charts
US9606986B2 (en) 2014-09-29 2017-03-28 Apple Inc. Integrated word N-gram and class M-gram language models
US10127911B2 (en) 2014-09-30 2018-11-13 Apple Inc. Speaker identification and unsupervised speaker adaptation techniques
US9886432B2 (en) 2014-09-30 2018-02-06 Apple Inc. Parsimonious handling of word inflection via categorical stem + suffix N-gram language models
US9668121B2 (en) 2014-09-30 2017-05-30 Apple Inc. Social reminders
US9646609B2 (en) 2014-09-30 2017-05-09 Apple Inc. Caching apparatus for serving phonetic pronunciations
US10074360B2 (en) 2014-09-30 2018-09-11 Apple Inc. Providing an indication of the suitability of speech recognition
US10552013B2 (en) 2014-12-02 2020-02-04 Apple Inc. Data detection
US9711141B2 (en) 2014-12-09 2017-07-18 Apple Inc. Disambiguating heteronyms in speech synthesis
US9865280B2 (en) 2015-03-06 2018-01-09 Apple Inc. Structured dictation using intelligent automated assistants
US10567477B2 (en) 2015-03-08 2020-02-18 Apple Inc. Virtual assistant continuity
US9721566B2 (en) 2015-03-08 2017-08-01 Apple Inc. Competing devices responding to voice triggers
US9886953B2 (en) 2015-03-08 2018-02-06 Apple Inc. Virtual assistant activation
US9899019B2 (en) 2015-03-18 2018-02-20 Apple Inc. Systems and methods for structured stem and suffix language models
US9842105B2 (en) 2015-04-16 2017-12-12 Apple Inc. Parsimonious continuous-space phrase representations for natural language processing
US10083688B2 (en) 2015-05-27 2018-09-25 Apple Inc. Device voice control for selecting a displayed affordance
US10127220B2 (en) 2015-06-04 2018-11-13 Apple Inc. Language identification from short strings
US10101822B2 (en) 2015-06-05 2018-10-16 Apple Inc. Language input correction
US10186254B2 (en) 2015-06-07 2019-01-22 Apple Inc. Context-based endpoint detection
US11025565B2 (en) 2015-06-07 2021-06-01 Apple Inc. Personalized prediction of responses for instant messaging
US10255907B2 (en) 2015-06-07 2019-04-09 Apple Inc. Automatic accent detection using acoustic models
US10747498B2 (en) 2015-09-08 2020-08-18 Apple Inc. Zero latency digital assistant
US10671428B2 (en) 2015-09-08 2020-06-02 Apple Inc. Distributed personal assistant
US9697820B2 (en) 2015-09-24 2017-07-04 Apple Inc. Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks
US11010550B2 (en) 2015-09-29 2021-05-18 Apple Inc. Unified language modeling framework for word prediction, auto-completion and auto-correction
US10366158B2 (en) 2015-09-29 2019-07-30 Apple Inc. Efficient word encoding for recurrent neural network language models
US11587559B2 (en) 2015-09-30 2023-02-21 Apple Inc. Intelligent device identification
US10691473B2 (en) 2015-11-06 2020-06-23 Apple Inc. Intelligent automated assistant in a messaging environment
US10049668B2 (en) 2015-12-02 2018-08-14 Apple Inc. Applying neural network language models to weighted finite state transducers for automatic speech recognition
JP6070809B1 (ja) * 2015-12-03 2017-02-01 国立大学法人静岡大学 自然言語処理装置及び自然言語処理方法
US10223066B2 (en) 2015-12-23 2019-03-05 Apple Inc. Proactive assistance based on dialog communication between devices
US10446143B2 (en) 2016-03-14 2019-10-15 Apple Inc. Identification of voice inputs providing credentials
US11025741B2 (en) 2016-05-25 2021-06-01 International Business Machines Corporation Dynamic cognitive user interface
US9934775B2 (en) 2016-05-26 2018-04-03 Apple Inc. Unit-selection text-to-speech synthesis based on predicted concatenation parameters
US9972304B2 (en) 2016-06-03 2018-05-15 Apple Inc. Privacy preserving distributed evaluation framework for embedded personalized systems
US10249300B2 (en) 2016-06-06 2019-04-02 Apple Inc. Intelligent list reading
US10049663B2 (en) 2016-06-08 2018-08-14 Apple, Inc. Intelligent automated assistant for media exploration
DK179309B1 (en) 2016-06-09 2018-04-23 Apple Inc Intelligent automated assistant in a home environment
US10067938B2 (en) 2016-06-10 2018-09-04 Apple Inc. Multilingual word prediction
US10192552B2 (en) 2016-06-10 2019-01-29 Apple Inc. Digital assistant providing whispered speech
US10490187B2 (en) 2016-06-10 2019-11-26 Apple Inc. Digital assistant providing automated status report
US10586535B2 (en) 2016-06-10 2020-03-10 Apple Inc. Intelligent digital assistant in a multi-tasking environment
US10509862B2 (en) 2016-06-10 2019-12-17 Apple Inc. Dynamic phrase expansion of language input
DK201670540A1 (en) 2016-06-11 2018-01-08 Apple Inc Application integration with a digital assistant
DK179343B1 (en) 2016-06-11 2018-05-14 Apple Inc Intelligent task discovery
DK179415B1 (en) 2016-06-11 2018-06-14 Apple Inc Intelligent device arbitration and control
DK179049B1 (en) 2016-06-11 2017-09-18 Apple Inc Data driven natural language event detection and classification
US10593346B2 (en) 2016-12-22 2020-03-17 Apple Inc. Rank-reduced token representation for automatic speech recognition
DK179745B1 (en) 2017-05-12 2019-05-01 Apple Inc. SYNCHRONIZATION AND TASK DELEGATION OF A DIGITAL ASSISTANT
DK201770431A1 (en) 2017-05-15 2018-12-20 Apple Inc. Optimizing dialogue policy decisions for digital assistants using implicit feedback
US10864443B2 (en) 2017-12-22 2020-12-15 Activision Publishing, Inc. Video game content aggregation, normalization, and publication systems and methods
US11106642B2 (en) 2018-12-26 2021-08-31 Io-Tahoe LLC. Cataloging database metadata using a probabilistic signature matching process
US11347813B2 (en) 2018-12-26 2022-05-31 Hitachi Vantara Llc Cataloging database metadata using a signature matching process
US11712627B2 (en) 2019-11-08 2023-08-01 Activision Publishing, Inc. System and method for providing conditional access to virtual gaming items

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4688195A (en) * 1983-01-28 1987-08-18 Texas Instruments Incorporated Natural-language interface generating system
JPS6140672A (ja) * 1984-07-31 1986-02-26 Hitachi Ltd 多品詞解消処理方式
US4887212A (en) * 1986-10-29 1989-12-12 International Business Machines Corporation Parser for natural language text
JP2664915B2 (ja) * 1988-01-12 1997-10-22 株式会社日立製作所 情報検索システム
US4994966A (en) * 1988-03-31 1991-02-19 Emerson & Stern Associates, Inc. System and method for natural language parsing by initiating processing prior to entry of complete sentences
US5197005A (en) * 1989-05-01 1993-03-23 Intelligent Business Systems Database retrieval system having a natural language interface
JPH03218570A (ja) * 1989-11-07 1991-09-26 Sharp Corp 文字列検索装置
US5175814A (en) * 1990-01-30 1992-12-29 Digital Equipment Corporation Direct manipulation interface for boolean information retrieval

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0585079A1 (de) * 1992-08-21 1994-03-02 Canon Kabushiki Kaisha Verfahren und Vorrichtung zur Verarbeitung von Signalen
WO1994004978A1 (en) * 1992-08-21 1994-03-03 Canon Inc Signal processing method and apparatus
US5870701A (en) * 1992-08-21 1999-02-09 Canon Kabushiki Kaisha Control signal processing method and apparatus having natural language interfacing capabilities
US5495604A (en) * 1993-08-25 1996-02-27 Asymetrix Corporation Method and apparatus for the modeling and query of database structures using natural language-like constructs
EP0715739A4 (de) * 1993-08-25 1998-04-01 Asymetrix Corp Verfahren und gerät zur modellierung und abfrage von datenbankenstrukturen mit natürlichen sprachartigen konstruktionen
US6202064B1 (en) 1997-06-20 2001-03-13 Xerox Corporation Linguistic search system
WO2000007117A3 (en) * 1998-07-30 2000-05-18 British Telecomm An index to a semi-structured database
US7409381B1 (en) 1998-07-30 2008-08-05 British Telecommunications Public Limited Company Index to a semi-structured database
GB2358937A (en) * 1999-09-03 2001-08-08 Ibm Hierarchical translation of a natural language statement to a formal command in a computer system
GB2358937B (en) * 1999-09-03 2004-03-17 Ibm Method and system for natural language understanding
WO2001040989A3 (de) * 1999-10-28 2002-07-18 Kiwilogic Com Ag Verfahren zur erweiterung einer datenbank bestehend aus datenpaaren aus einander zugeordneter erkennung und antwort
DE19952769B4 (de) * 1999-11-02 2008-07-17 Sap Ag Suchmaschine und Verfahren zum Abrufen von Informationen mit Abfragen in natürlicher Sprache
DE19952769A1 (de) * 1999-11-02 2001-05-03 Sap Ag System und Verfahren zum Abrufen von Informationen mit Abfragen in natürlicher Sprache
US6741959B1 (en) 1999-11-02 2004-05-25 Sap Aktiengesellschaft System and method to retrieving information with natural language queries
WO2002010981A3 (en) * 2000-07-28 2003-12-31 Easyask Inc Distributed search system and method
WO2004012066A3 (en) * 2002-07-29 2004-07-29 Electronic Data Syst Corp Interactive natural language query processing system and method
US7246116B2 (en) * 2004-04-22 2007-07-17 International Business Machines Corporation Method, system and article of manufacturing for converting data values quantified using a first measurement unit into equivalent data values when quantified using a second measurement unit in order to receive query results including data values measured using at least one of the first and second measurement units
US7362075B2 (en) 2004-06-08 2008-04-22 Friwo Geraetebau Gmbh Battery charger with charge state detection on the primary side
WO2007044434A3 (en) * 2005-10-05 2007-07-26 Piper Communications Inc Systems and methods for electronic searching of automotive parts database
CN106021232A (zh) * 2016-05-24 2016-10-12 北京工商大学 一种基于依存句法关系的微博马甲账号识别方法
CN106021232B (zh) * 2016-05-24 2019-06-28 北京工商大学 一种基于依存句法关系的微博马甲账号识别方法

Also Published As

Publication number Publication date
EP0522591B1 (de) 2000-03-22
EP0522591A3 (en) 1993-11-03
US5442780A (en) 1995-08-15
DE69230814T2 (de) 2000-11-02
DE69230814D1 (de) 2000-04-27

Similar Documents

Publication Publication Date Title
US5442780A (en) Natural language database retrieval system using virtual tables to convert parsed input phrases into retrieval keys
US6081774A (en) Natural language information retrieval system and method
US5732274A (en) Method for compilation using a database for target language independence
US5555169A (en) Computer system and method for converting a conversational statement to computer command language
EP1399842B1 (de) Erstellung von strukturierten daten aus unformatiertem text
US5424947A (en) Natural language analyzing apparatus and method, and construction of a knowledge base for natural language analysis
US5123103A (en) Method and system of retrieving program specification and linking the specification by concept to retrieval request for reusing program parts
US6272495B1 (en) Method and apparatus for processing free-format data
EP0610760B1 (de) Dokumentenerkennungssystem mit verbesserter Wirksamkeit der Dokumentenerkennung
US6766330B1 (en) Universal output constructor for XML queries universal output constructor for XML queries
US5197005A (en) Database retrieval system having a natural language interface
KR100396462B1 (ko) 메시지 변환 선택 툴 및 그 방법
US6523172B1 (en) Parser translator system and method
US6493663B1 (en) Document summarizing apparatus, document summarizing method and recording medium carrying a document summarizing program
JP3266586B2 (ja) データ分析システム
US20100250598A1 (en) Graph based re-composition of document fragments for name entity recognition under exploitation of enterprise databases
JP2008033931A (ja) テキストを追補する方法、クエリーに応答してテキストを取得する方法、およびシステム
Beckwith et al. Implementing a lexical network
CN108766507A (zh) 一种基于CQL与标准信息模型openEHR的临床质量指标计算方法
JP2596260B2 (ja) 対応表使用データベース検索装置
CN120011385A (zh) 基于自然语言的数据库查询方法、装置、设备及介质
Kellogg On-line translation of natural language questions into artificial language queries
AU774729B2 (en) Method and apparatus for processing free-format data
JP3014237B2 (ja) 日本語解析装置
Wachowiak Introduction to Text Analysis In R

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 19920710

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): DE FR GB

PUAL Search report despatched

Free format text: ORIGINAL CODE: 0009013

AK Designated contracting states

Kind code of ref document: A3

Designated state(s): DE FR GB

17Q First examination report despatched

Effective date: 19980602

GRAG Despatch of communication of intention to grant

Free format text: ORIGINAL CODE: EPIDOS AGRA

RIC1 Information provided on ipc code assigned before grant

Free format text: 6G 06F 17/30 A

GRAG Despatch of communication of intention to grant

Free format text: ORIGINAL CODE: EPIDOS AGRA

GRAH Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOS IGRA

GRAH Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOS IGRA

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): DE FR GB

REF Corresponds to:

Ref document number: 69230814

Country of ref document: DE

Date of ref document: 20000427

ET Fr: translation filed
PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

26N No opposition filed
REG Reference to a national code

Ref country code: GB

Ref legal event code: IF02

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20060705

Year of fee payment: 15

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 20060706

Year of fee payment: 15

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 20060719

Year of fee payment: 15

GBPC Gb: european patent ceased through non-payment of renewal fee

Effective date: 20070710

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20080201

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GB

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20070710

REG Reference to a national code

Ref country code: FR

Ref legal event code: ST

Effective date: 20080331

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: FR

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20070731